Repeating these sort of tests on a quad core (rather than my dual core)
would be interesting. I have no idea how this goes through cores.
This is essentially to localhost on my netns setup:
root@nemesis:~/git/netem-scripts/veth# ip netns exec client irtt client -i 1ms
-d 10s -q 10.10.2.2
Min Mean Median Max Stddev
--- ---- ------ --- ------
RTT 28.8µs 161µs 130µs 4.97ms 148µs
send delay 16.2µs 88.3µs 70.9µs 2.76ms 94.5µs
receive delay 11.6µs 72.6µs 59.1µs 4.88ms 98.8µs
IPDV (jitter) 6ns 59.5µs 25.4µs 4.86ms 138µs
send IPDV 0s 34.4µs 14.5µs 2.54ms 96.5µs
receive IPDV 0s 30.1µs 13.1µs 4.81ms 94.9µs
send call time 8.14µs 43.6µs 1.7ms 34.4µs
timer error 0s 21.2µs 2.32ms 58µs
server proc. time 1.85µs 16.4µs 755µs 13.9µs
duration: 10s (wait 14.9ms)
packets sent/received: 9888/9888 (0.00% loss)
server packets received: 9888/9888 (0.00%/0.00% upstream/downstream loss)
bytes sent/received: 593280/593280
send/receive rate: 474.7 Kbps / 474.7 Kbps
packet length: 60 bytes
timer stats: 112/10000 (1.12%) missed, 2.12% error
This is to a 15mbit/1mbit emulated dsl link with atm framing with 10ms delay
each way.
root@nemesis:~/git/netem-scripts/veth# ip netns exec server irtt client -i 1ms
-d 10s -q 10.10.2.2
Min Mean Median Max Stddev
--- ---- ------ --- ------
RTT 22.2ms 941.5ms 1.17s 1.29s 415.7ms
send delay 10.1ms 10.2ms 10.18ms 14ms 122µs
receive delay 11.71ms 931.3ms 1.16s 1.28s 415.7ms
IPDV (jitter) 176ns 286µs 274µs 7.42ms 152µs
send IPDV 0s 46.9µs 21.6µs 2.48ms 113µs
receive IPDV 247ns 291µs 276µs 7.4ms 178µs
send call time 5.83µs 41.5µs 2.57ms 54.7µs
timer error 2ns 25.5µs 3.24ms 80.9µs
server proc. time 2.02µs 15.4µs 858µs 18.8µs
duration: 13.9s (wait 3.88s)
packets sent/received: 9845/8859 (10.02% loss)
server packets received: 9845/9845 (0.00%/10.02% upstream/downstream loss)
bytes sent/received: 590700/531540
send/receive rate: 472.6 Kbps / 377.4 Kbps
packet length: 60 bytes
timer stats: 154/9999 (1.54%) missed, 2.55% error
since 60 byte packets explode to 96 or more, and 1mbit not enough...
ip netns exec server irtt client -i 20ms -d 10s -q 10.10.2.2
Min Mean Median Max Stddev
--- ---- ------ --- ------
RTT 21.6ms 22.02ms 22.01ms 24.14ms 186µs
send delay 10.2ms 10.41ms 10.4ms 11.08ms 110µs
receive delay 11.37ms 11.61ms 11.6ms 13.68ms 126µs
IPDV (jitter) 516ns 252µs 245µs 2.38ms 183µs
send IPDV 1.17µs 165µs 161µs 645µs 94µs
receive IPDV 624ns 122µs 102µs 2.24ms 152µs
send call time 38.5µs 118µs 339µs 60.8µs
timer error 81ns 25.7µs 215µs 24.1µs
server proc. time 9.07µs 36.7µs 109µs 18.5µs
duration: 10.1s (wait 72.42ms)
packets sent/received: 499/499 (0.00% loss)
server packets received: 499/499 (0.00%/0.00% upstream/downstream loss)
bytes sent/received: 29940/29940
send/receive rate: 24.0 Kbps / 24.0 Kbps
packet length: 60 bytes
timer stats: 1/500 (0.20%) missed, 0.13% error
[CloseConn] close from 10.10.0.1:49155, token a472c579548c690a
Pete Heist <notificati...@github.com> writes:
> I really like these PCEngines APU2 boards, and PTP HW timestamps. Now Peter,
> back to work... :)
>
> sysadmin@apu2a:~$ ./irtt client -i 1ms -d 10s -q 10.9.0.2
> [Connecting] connecting to 10.9.0.2
> [Connected] connected to 10.9.0.2:2112
>
> Min Mean Median Max Stddev
> --- ---- ------ --- ------
> RTT 237µs 270µs 268µs 366µs 10µs
> send delay 119µs 135µs 134µs 226µs 7.34µs
> receive delay 113µs 135µs 134µs 227µs 6.25µs
>
> IPDV (jitter) 1ns 9.47µs 6.32µs 107µs 9.86µs
> send IPDV 0s 6.96µs 4.71µs 90.1µs 7.43µs
> receive IPDV 0s 4.92µs 2.61µs 92.5µs 6.84µs
> ...
>
> —
> You are receiving this because you commented.
> Reply to this email directly, view it on GitHub, or mute the thread.
--
You are receiving this because you commented.
Reply to this email directly or view it on GitHub:
https://github.com/tohojo/flent/issues/106#issuecomment-343635972_______________________________________________
Flent-users mailing list
Flent-users@flent.org
http://flent.org/mailman/listinfo/flent-users_flent.org
